© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18516
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with the letter "A"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'A' as a standalone character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optics
    -0.68
    enegger
    -0.64
     upstairs
    -0.61
     negatives
    -0.58
     enclosed
    -0.57
     outl
    -0.57
     IPS
    -0.56
     accuracy
    -0.55
     intended
    -0.55
     overt
    -0.54
    POSITIVE LOGITS
    cknow
    1.27
    cknowled
    1.23
    perture
    1.21
    ussie
    1.19
    verages
    1.17
    uctions
    1.11
    ileen
    1.08
    HA
    1.05
    BILITIES
    1.04
    UG
    1.02
    Activations Density 0.072%

    No Known Activations